Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference

Computer Science > Cryptography and Security [Submitted on 20 Mar 2026] Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference Bernardo Magri, Benjamin Marsh, Paul Gebheim Modern cloud inference creates a two sided privacy problem where users reveal sensitive inputs to providers, while providers must execute proprietary model weights inside potentially leaky execution environments. Fully homomorphic encryption (FHE) offers cryptographic guarantees but remains prohibitively expensive for modern architectures. We argue that progress requires co-design where specializing FHE schemes/compilers for the static structure of inference circuits, while simultaneously constraining inference architectures to reduce dominant homomorphic cost drivers. We outline a meet in the middle agenda and concrete optimization targets on both axes. Comments: Accepted to AICrypt 2026 Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.20504 [cs.CR]   (or arXiv:2603.20504v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.20504 Focus to learn more Submission history From: Benjamin Marsh [view email] [v1] Fri, 20 Mar 2026 21:16:58 UTC (9 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)